You don’t think nearly 1/6th is statistically significant?
For statistics’ sake? Yes.
For the LLM bias? No.
Comment on Meta AI is obsessed with turbans when generating images of Indian men
HopeOfTheGunblade@kbin.social 6 months agoYou don't think nearly 1/6th is statistically significant? What's the lower bound on significance as you see things?
To be clear, it's obviously dumb for their generative system to be overrepresenting turbans like this, although it's likely to be a bias in the inputs rather than something the system came up with itself, I just think that 5% is generally enough to be considered significant and calling three times that not significant confuses me.
0x0@programming.dev 6 months ago
SavedKriss@lemmy.world 6 months ago
-
It’s not an LLM, it’s a GAN and it’s inner workings are very different.
-
If that 1/6th has the most positive feedback in recognizability, for the GAN it becomes a high weighted part of the standard. These model’s categorizing flow favors unique features of images.
-
FarceOfWill@infosec.pub 6 months ago
5/6 not wearing them seems more statistically significant
tabular@lemmy.world 6 months ago
The fact less people of that group actually wear it than do is significant when you want an average sample. When categorizing a collection of images then, naturally, the traditional garments of a group is associated more with that group than than any other group: 1/6 is bigger than any other race combined.
Womble@lemmy.world 6 months ago
so if there was a country where 1 in 6 people had blue skin you would consider that statistically insignificant because 5 out of 6 didn’t?
sugar_in_your_tea@sh.itjust.works 6 months ago
For a caricature of the population? Yes, that’s not what the algorithm should be optimising for.
SavedKriss@lemmy.world 6 months ago
The algorithm is optimizing for results that are rated as precise, not just frequent.